Claude 3.7 Sonnet vs Mistral Devstral Medium
Compare Claude 3.7 Sonnet by Anthropic against Mistral Devstral Medium by Mistral AI, tested across 55 shared challenges.
Our Verdict
Claude 3.7 Sonnet
Mistral Devstral MediumRunner-up
No community votes yet. On paper, Claude 3.7 Sonnet has the edge — bigger model tier, bigger context window, major provider backing.
Mistral Devstral Medium is 7.5x cheaper per token — worth considering if cost matters.
Too close to call
API pricing
Cost per 1M tokens
Claude 3.7 Sonnet
Input
$3.00
Output
$15.00
Mistral Devstral Medium
Input
$0.40
7.5× cheaper
Output
$2.00
7.5× cheaper
Mistral Devstral Medium is cheaper on both — 7.5× input, 7.5× output
Writing DNA
Style Comparison
Similarity
59%
Claude 3.7 Sonnet uses 9.3x more headings
Claude 3.7 Sonnet
Mistral Devstral Medium
62%Vocabulary50%
35wSentence Length17w
0.99Hedging0.56
1.2Bold4.5
4.3Lists5.3
0.00Emoji0.00
1.78Headings0.19
0.23Transitions0.32
Based on 13 + 21 text responses
Research
What we learned reading every model
FAQ
